Neural network topology optimization
Identifieur interne :
000551 ( PascalFrancis/Curation );
précédent :
000550;
suivant :
000552
Neural network topology optimization
Auteurs : Mohammed Attik [
France] ;
Laurent Bougrain [
France] ;
Frédéric Alexandre [
France]
Source :
-
Lecture notes in computer science [ 0302-9743 ] ; 2005.
RBID : Pascal:06-0067795
Descripteurs français
- Pascal (Inist)
- Méthode formelle,
Haute performance,
Intelligence artificielle,
Solution optimale,
Classification,
Topologie circuit,
Réseau neuronal,
Optimisation,
Méthode optimisation,
Algorithme apprentissage,
..
- Wicri :
English descriptors
Abstract
The determination of the optimal architecture of a supervised neural network is an important and a difficult task. The classical neural network topology optimization methods select weight(s) or unit(s) from the architecture in order to give a high performance of a learning algorithm. However, all existing topology optimization methods do not guarantee to obtain the optimal solution. In this work, we propose a hybrid approach which combines variable selection method and classical optimization method in order to improve optimization topology solution. The proposed approach suggests to identify the relevant subset of variables which gives a good classification performance in the first step and then to apply a classical topology optimization method to eliminate unnecessary hidden units or weights. A comparison of our approach to classical techniques for architecture optimization is given.
| pA |
| A01 | 01 | 1 | | @0 0302-9743 |
|---|
| A05 | | | | @2 3697 |
|---|
| A08 | 01 | 1 | ENG | @1 Neural network topology optimization |
|---|
| A09 | 01 | 1 | ENG | @1 Artificial neural networks. Part II : formal models and their applications : ICANN 2005 : 15th International Conference, Warsaw, Poland, September 11-15, 2005 : proceedings |
|---|
| A11 | 01 | 1 | | @1 ATTIK (Mohammed) |
|---|
| A11 | 02 | 1 | | @1 BOUGRAIN (Laurent) |
|---|
| A11 | 03 | 1 | | @1 ALEXANDRE (Frédéric) |
|---|
| A14 | 01 | | | @1 LORIA/INRIA-Lorraine, Campus Scientifique - BP 239 @2 54506, Vandœuvre-lès-Nancy @3 FRA @Z 1 aut. @Z 2 aut. @Z 3 aut. |
|---|
| A14 | 02 | | | @1 BRGM, 3 av Claude Guillemin - BP 6009 @2 45060 Orléans @3 FRA @Z 1 aut. |
|---|
| A20 | | | | @1 53-58 |
|---|
| A21 | | | | @1 2005 |
|---|
| A23 | 01 | | | @0 ENG |
|---|
| A26 | 01 | | | @0 3-540-28755-8 |
|---|
| A43 | 01 | | | @1 INIST @2 16343 @5 354000138682610090 |
|---|
| A44 | | | | @0 0000 @1 © 2006 INIST-CNRS. All rights reserved. |
|---|
| A45 | | | | @0 12 ref. |
|---|
| A47 | 01 | 1 | | @0 06-0067795 |
|---|
| A60 | | | | @1 P @2 C |
|---|
| A61 | | | | @0 A |
|---|
| A64 | 01 | 1 | | @0 Lecture notes in computer science |
|---|
| A66 | 01 | | | @0 DEU |
|---|
| C01 | 01 | | ENG | @0 The determination of the optimal architecture of a supervised neural network is an important and a difficult task. The classical neural network topology optimization methods select weight(s) or unit(s) from the architecture in order to give a high performance of a learning algorithm. However, all existing topology optimization methods do not guarantee to obtain the optimal solution. In this work, we propose a hybrid approach which combines variable selection method and classical optimization method in order to improve optimization topology solution. The proposed approach suggests to identify the relevant subset of variables which gives a good classification performance in the first step and then to apply a classical topology optimization method to eliminate unnecessary hidden units or weights. A comparison of our approach to classical techniques for architecture optimization is given. |
|---|
| C02 | 01 | X | | @0 001D02C |
|---|
| C03 | 01 | X | FRE | @0 Méthode formelle @5 01 |
|---|
| C03 | 01 | X | ENG | @0 Formal method @5 01 |
|---|
| C03 | 01 | X | SPA | @0 Método formal @5 01 |
|---|
| C03 | 02 | X | FRE | @0 Haute performance @5 06 |
|---|
| C03 | 02 | X | ENG | @0 High performance @5 06 |
|---|
| C03 | 02 | X | SPA | @0 Alto rendimiento @5 06 |
|---|
| C03 | 03 | X | FRE | @0 Intelligence artificielle @5 07 |
|---|
| C03 | 03 | X | ENG | @0 Artificial intelligence @5 07 |
|---|
| C03 | 03 | X | SPA | @0 Inteligencia artificial @5 07 |
|---|
| C03 | 04 | X | FRE | @0 Solution optimale @5 08 |
|---|
| C03 | 04 | X | ENG | @0 Optimal solution @5 08 |
|---|
| C03 | 04 | X | SPA | @0 Solución óptima @5 08 |
|---|
| C03 | 05 | X | FRE | @0 Classification @5 09 |
|---|
| C03 | 05 | X | ENG | @0 Classification @5 09 |
|---|
| C03 | 05 | X | SPA | @0 Clasificación @5 09 |
|---|
| C03 | 06 | 3 | FRE | @0 Topologie circuit @5 18 |
|---|
| C03 | 06 | 3 | ENG | @0 Network topology @5 18 |
|---|
| C03 | 07 | X | FRE | @0 Réseau neuronal @5 23 |
|---|
| C03 | 07 | X | ENG | @0 Neural network @5 23 |
|---|
| C03 | 07 | X | SPA | @0 Red neuronal @5 23 |
|---|
| C03 | 08 | X | FRE | @0 Optimisation @5 24 |
|---|
| C03 | 08 | X | ENG | @0 Optimization @5 24 |
|---|
| C03 | 08 | X | SPA | @0 Optimización @5 24 |
|---|
| C03 | 09 | X | FRE | @0 Méthode optimisation @5 25 |
|---|
| C03 | 09 | X | ENG | @0 Optimization method @5 25 |
|---|
| C03 | 09 | X | SPA | @0 Método optimización @5 25 |
|---|
| C03 | 10 | X | FRE | @0 Algorithme apprentissage @5 26 |
|---|
| C03 | 10 | X | ENG | @0 Learning algorithm @5 26 |
|---|
| C03 | 10 | X | SPA | @0 Algoritmo aprendizaje @5 26 |
|---|
| C03 | 11 | X | FRE | @0 . @4 INC @5 82 |
|---|
| N21 | | | | @1 037 |
|---|
| N44 | 01 | | | @1 OTO |
|---|
| N82 | | | | @1 OTO |
|---|
|
|---|
| pR |
| A30 | 01 | 1 | ENG | @1 International Conference on Artificial Neural Networks @2 15 @3 Warsaw POL @4 2005-09-11 |
|---|
|
|---|
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: Pour aller vers cette notice dans l'étape Curation :000482
Links to Exploration step
Pascal:06-0067795
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Neural network topology optimization</title>
<author><name sortKey="Attik, Mohammed" sort="Attik, Mohammed" uniqKey="Attik M" first="Mohammed" last="Attik">Mohammed Attik</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>LORIA/INRIA-Lorraine, Campus Scientifique - BP 239</s1>
<s2>54506, Vandœuvre-lès-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14><country>France</country>
</affiliation><affiliation wicri:level="1"><inist:fA14 i1="02"><s1>BRGM, 3 av Claude Guillemin - BP 6009</s1>
<s2>45060 Orléans</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
</inist:fA14><country>France</country>
</affiliation><author><name sortKey="Bougrain, Laurent" sort="Bougrain, Laurent" uniqKey="Bougrain L" first="Laurent" last="Bougrain">Laurent Bougrain</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>LORIA/INRIA-Lorraine, Campus Scientifique - BP 239</s1>
<s2>54506, Vandœuvre-lès-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14><country>France</country>
</affiliation><author><name sortKey="Alexandre, Frederic" sort="Alexandre, Frederic" uniqKey="Alexandre F" first="Frédéric" last="Alexandre">Frédéric Alexandre</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>LORIA/INRIA-Lorraine, Campus Scientifique - BP 239</s1>
<s2>54506, Vandœuvre-lès-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14><country>France</country>
</affiliation><publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">06-0067795</idno>
<date when="2005">2005</date>
<idno type="stanalyst">PASCAL 06-0067795 INIST</idno>
<idno type="RBID">Pascal:06-0067795</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000482</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000551</idno>
</publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Neural network topology optimization</title>
<author><name sortKey="Attik, Mohammed" sort="Attik, Mohammed" uniqKey="Attik M" first="Mohammed" last="Attik">Mohammed Attik</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>LORIA/INRIA-Lorraine, Campus Scientifique - BP 239</s1>
<s2>54506, Vandœuvre-lès-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14><country>France</country>
</affiliation><affiliation wicri:level="1"><inist:fA14 i1="02"><s1>BRGM, 3 av Claude Guillemin - BP 6009</s1>
<s2>45060 Orléans</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
</inist:fA14><country>France</country>
</affiliation><author><name sortKey="Bougrain, Laurent" sort="Bougrain, Laurent" uniqKey="Bougrain L" first="Laurent" last="Bougrain">Laurent Bougrain</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>LORIA/INRIA-Lorraine, Campus Scientifique - BP 239</s1>
<s2>54506, Vandœuvre-lès-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14><country>France</country>
</affiliation><author><name sortKey="Alexandre, Frederic" sort="Alexandre, Frederic" uniqKey="Alexandre F" first="Frédéric" last="Alexandre">Frédéric Alexandre</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>LORIA/INRIA-Lorraine, Campus Scientifique - BP 239</s1>
<s2>54506, Vandœuvre-lès-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14><country>France</country>
</affiliation><series><title level="j" type="main">Lecture notes in computer science</title>
<idno type="ISSN">0302-9743</idno>
<imprint><date when="2005">2005</date>
</imprint><seriesStmt><title level="j" type="main">Lecture notes in computer science</title>
<idno type="ISSN">0302-9743</idno>
</seriesStmt><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Artificial intelligence</term>
<term>Classification</term>
<term>Formal method</term>
<term>High performance</term>
<term>Learning algorithm</term>
<term>Network topology</term>
<term>Neural network</term>
<term>Optimal solution</term>
<term>Optimization</term>
<term>Optimization method</term>
</keywords><keywords scheme="Pascal" xml:lang="fr"><term>Méthode formelle</term>
<term>Haute performance</term>
<term>Intelligence artificielle</term>
<term>Solution optimale</term>
<term>Classification</term>
<term>Topologie circuit</term>
<term>Réseau neuronal</term>
<term>Optimisation</term>
<term>Méthode optimisation</term>
<term>Algorithme apprentissage</term>
<term>.</term>
</keywords><keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Intelligence artificielle</term>
<term>Classification</term>
</keywords><front><div type="abstract" xml:lang="en">The determination of the optimal architecture of a supervised neural network is an important and a difficult task. The classical neural network topology optimization methods select weight(s) or unit(s) from the architecture in order to give a high performance of a learning algorithm. However, all existing topology optimization methods do not guarantee to obtain the optimal solution. In this work, we propose a hybrid approach which combines variable selection method and classical optimization method in order to improve optimization topology solution. The proposed approach suggests to identify the relevant subset of variables which gives a good classification performance in the first step and then to apply a classical topology optimization method to eliminate unnecessary hidden units or weights. A comparison of our approach to classical techniques for architecture optimization is given.</div>
</front><inist><standard h6="B"><pA><fA01 i1="01" i2="1"><s0>0302-9743</s0>
</fA01><fA05><s2>3697</s2>
</fA05><fA08 i1="01" i2="1" l="ENG"><s1>Neural network topology optimization</s1>
</fA08><fA09 i1="01" i2="1" l="ENG"><s1>Artificial neural networks. Part II : formal models and their applications : ICANN 2005 : 15th International Conference, Warsaw, Poland, September 11-15, 2005 : proceedings</s1>
</fA09><fA11 i1="01" i2="1"><s1>ATTIK (Mohammed)</s1>
</fA11><fA11 i1="02" i2="1"><s1>BOUGRAIN (Laurent)</s1>
</fA11><fA11 i1="03" i2="1"><s1>ALEXANDRE (Frédéric)</s1>
</fA11><fA14 i1="01"><s1>LORIA/INRIA-Lorraine, Campus Scientifique - BP 239</s1>
<s2>54506, Vandœuvre-lès-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</fA14><fA14 i1="02"><s1>BRGM, 3 av Claude Guillemin - BP 6009</s1>
<s2>45060 Orléans</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
</fA14><fA20><s1>53-58</s1>
</fA20><fA21><s1>2005</s1>
</fA21><fA23 i1="01"><s0>ENG</s0>
</fA23><fA26 i1="01"><s0>3-540-28755-8</s0>
</fA26><fA43 i1="01"><s1>INIST</s1>
<s2>16343</s2>
<s5>354000138682610090</s5>
</fA43><fA44><s0>0000</s0>
<s1>© 2006 INIST-CNRS. All rights reserved.</s1>
</fA44><fA45><s0>12 ref.</s0>
</fA45><fA47 i1="01" i2="1"><s0>06-0067795</s0>
</fA47><fA60><s1>P</s1>
<s2>C</s2>
</fA60><fA64 i1="01" i2="1"><s0>Lecture notes in computer science</s0>
</fA64><fA66 i1="01"><s0>DEU</s0>
</fA66><fC01 i1="01" l="ENG"><s0>The determination of the optimal architecture of a supervised neural network is an important and a difficult task. The classical neural network topology optimization methods select weight(s) or unit(s) from the architecture in order to give a high performance of a learning algorithm. However, all existing topology optimization methods do not guarantee to obtain the optimal solution. In this work, we propose a hybrid approach which combines variable selection method and classical optimization method in order to improve optimization topology solution. The proposed approach suggests to identify the relevant subset of variables which gives a good classification performance in the first step and then to apply a classical topology optimization method to eliminate unnecessary hidden units or weights. A comparison of our approach to classical techniques for architecture optimization is given.</s0>
</fC01><fC02 i1="01" i2="X"><s0>001D02C</s0>
</fC02><fC03 i1="01" i2="X" l="FRE"><s0>Méthode formelle</s0>
<s5>01</s5>
</fC03><fC03 i1="01" i2="X" l="ENG"><s0>Formal method</s0>
<s5>01</s5>
</fC03><fC03 i1="01" i2="X" l="SPA"><s0>Método formal</s0>
<s5>01</s5>
</fC03><fC03 i1="02" i2="X" l="FRE"><s0>Haute performance</s0>
<s5>06</s5>
</fC03><fC03 i1="02" i2="X" l="ENG"><s0>High performance</s0>
<s5>06</s5>
</fC03><fC03 i1="02" i2="X" l="SPA"><s0>Alto rendimiento</s0>
<s5>06</s5>
</fC03><fC03 i1="03" i2="X" l="FRE"><s0>Intelligence artificielle</s0>
<s5>07</s5>
</fC03><fC03 i1="03" i2="X" l="ENG"><s0>Artificial intelligence</s0>
<s5>07</s5>
</fC03><fC03 i1="03" i2="X" l="SPA"><s0>Inteligencia artificial</s0>
<s5>07</s5>
</fC03><fC03 i1="04" i2="X" l="FRE"><s0>Solution optimale</s0>
<s5>08</s5>
</fC03><fC03 i1="04" i2="X" l="ENG"><s0>Optimal solution</s0>
<s5>08</s5>
</fC03><fC03 i1="04" i2="X" l="SPA"><s0>Solución óptima</s0>
<s5>08</s5>
</fC03><fC03 i1="05" i2="X" l="FRE"><s0>Classification</s0>
<s5>09</s5>
</fC03><fC03 i1="05" i2="X" l="ENG"><s0>Classification</s0>
<s5>09</s5>
</fC03><fC03 i1="05" i2="X" l="SPA"><s0>Clasificación</s0>
<s5>09</s5>
</fC03><fC03 i1="06" i2="3" l="FRE"><s0>Topologie circuit</s0>
<s5>18</s5>
</fC03><fC03 i1="06" i2="3" l="ENG"><s0>Network topology</s0>
<s5>18</s5>
</fC03><fC03 i1="07" i2="X" l="FRE"><s0>Réseau neuronal</s0>
<s5>23</s5>
</fC03><fC03 i1="07" i2="X" l="ENG"><s0>Neural network</s0>
<s5>23</s5>
</fC03><fC03 i1="07" i2="X" l="SPA"><s0>Red neuronal</s0>
<s5>23</s5>
</fC03><fC03 i1="08" i2="X" l="FRE"><s0>Optimisation</s0>
<s5>24</s5>
</fC03><fC03 i1="08" i2="X" l="ENG"><s0>Optimization</s0>
<s5>24</s5>
</fC03><fC03 i1="08" i2="X" l="SPA"><s0>Optimización</s0>
<s5>24</s5>
</fC03><fC03 i1="09" i2="X" l="FRE"><s0>Méthode optimisation</s0>
<s5>25</s5>
</fC03><fC03 i1="09" i2="X" l="ENG"><s0>Optimization method</s0>
<s5>25</s5>
</fC03><fC03 i1="09" i2="X" l="SPA"><s0>Método optimización</s0>
<s5>25</s5>
</fC03><fC03 i1="10" i2="X" l="FRE"><s0>Algorithme apprentissage</s0>
<s5>26</s5>
</fC03><fC03 i1="10" i2="X" l="ENG"><s0>Learning algorithm</s0>
<s5>26</s5>
</fC03><fC03 i1="10" i2="X" l="SPA"><s0>Algoritmo aprendizaje</s0>
<s5>26</s5>
</fC03><fC03 i1="11" i2="X" l="FRE"><s0>.</s0>
<s4>INC</s4>
<s5>82</s5>
</fC03><fN21><s1>037</s1>
</fN21><fN44 i1="01"><s1>OTO</s1>
</fN44><fN82><s1>OTO</s1>
</fN82><pR><fA30 i1="01" i2="1" l="ENG"><s1>International Conference on Artificial Neural Networks</s1>
<s2>15</s2>
<s3>Warsaw POL</s3>
<s4>2005-09-11</s4>
</fA30>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/PascalFrancis/Curation
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000551 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Curation/biblio.hfd -nk 000551 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Lorraine
|area= InforLorV4
|flux= PascalFrancis
|étape= Curation
|type= RBID
|clé= Pascal:06-0067795
|texte= Neural network topology optimization
}}
| This area was generated with Dilib version V0.6.33.
Data generation: Mon Jun 10 21:56:28 2019. Site generation: Fri Feb 25 15:29:27 2022 |  |
